mlx-community/Yi-1.5-6B-Chat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
73 vs 66
Hardware Fit
100 vs 91
Quality Score
62 vs 55
Hardware
mlx-community/Yi-1… qwen3.8-27b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM32 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/Yi-1… qwen3.8-27b-mlx
Tokens/sec29.133.2
First chunk451 ms7 ms
TTFT451 ms311 ms
Load timeN/AN/A
Memory usage0.9 GB0.5 GB
Memory %3%1%
HW Fit Score Breakdown
mlx-community/Yi-1.5-6B…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
mlx-community/Yi-1.5-6B…
Reasoning
10/20
Coding
11/20
Instruction
13/20
Structured
13/15
Math
9/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Adequate
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest